| --- |
| license: other |
| license_name: inf |
| license_link: https://huggingface.co/infly/OpenCoder-1.5B-Base/blob/main/LICENSE |
| language: |
| - en |
| - zh |
| base_model: infly/OpenCoder-1.5B-Base |
| pipeline_tag: text-generation |
| library_name: transformers |
| tags: |
| - code |
| --- |
| |
| ## Description |
|
|
| This model is derived from [OpenCoder-1.5B-Base](https://huggingface.co/infly/OpenCoder-1.5B-Base) by applying additional context extension fine-tuning. The repository context is composed using the _Code Chunks `.py` reversed_ composer, more details on which, along with others, can be found in the [On Pretraining for Project-Level Code Completion](https://openreview.net/forum?id=t9RN9WX4Ic) paper ([arxiv](https://arxiv.org/abs/2510.13697)). Specifically, Section A.1 of the Appendix describes the context composition method, and Table 3 provides a comparison with other composers from the same [collection](https://huggingface.co/collections/JetBrains-Research/repository-level-pre-trained-opencoder-68e938c003be1cfba9c3595e). |
|
|
| We publish this checkpoint to support the reproducibility and accessibility of our research results. |
|
|
| ## Quickstart |
|
|
| ```python |
| import torch |
| from transformers import AutoModelForCausalLM, AutoTokenizer |
| |
| model_name = "JetBrains-Research/OpenCoder-1.5B-Code-Chunks-Py-Reversed" |
| tokenizer_name = "infly/OpenCoder-1.5B-Base" |
| |
| model = AutoModelForCausalLM.from_pretrained(model_name, |
| torch_dtype=torch.bfloat16, |
| device_map="auto", |
| trust_remote_code=True) |
| tokenizer = AutoTokenizer.from_pretrained(tokenizer_name, trust_remote_code=True) |
| |
| inputs = tokenizer("# write a quick sort algorithm", return_tensors="pt") |
| outputs = model.generate(**inputs.to(model.device), max_new_tokens=256) |
| |
| result = tokenizer.decode(outputs[0], skip_special_tokens=True) |
| print(result) |
| ``` |
